Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3640 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1859. Min Act: -0.0000

Data Index: 301215 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1841. Min Act: 0.0001

Data Index: 586035 (C4 (Web Text))

Max Activating Token Index: 777

Text #2

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1640. Min Act: -0.0000

Data Index: 1129698 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1586. Min Act: 0.0000

Data Index: 530175 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1556. Min Act: -0.0000

Data Index: 777972 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1487. Min Act: -0.0000

Data Index: 791899 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1511. Min Act: 0.0000

Data Index: 897778 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1454. Min Act: -0.0000

Data Index: 263421 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1452. Min Act: 0.0000

Data Index: 214408 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1434. Min Act: -0.0000

Data Index: 788536 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1428. Min Act: -0.0000

Data Index: 1027531 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1413. Min Act: -0.0000

Data Index: 820233 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1402. Min Act: 0.0001

Data Index: 41959 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1366. Min Act: -0.0000

Data Index: 370501 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1321. Min Act: -0.0000

Data Index: 964758 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1353. Min Act: 0.0000

Data Index: 736143 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1275. Min Act: -0.0000

Data Index: 702123 (C4 (Web Text))

Max Activating Token Index: 835

Text #17

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1362. Min Act: -0.0000

Data Index: 783104 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1400. Min Act: -0.0000

Data Index: 603948 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1299. Min Act: -0.0000

Data Index: 802905 (C4 (Web Text))

Max Activating Token Index: 297